公开(公告)号：US12091043B2

公开(公告)日：2024-09-17

申请号：US18109113

申请日：2023-02-13

Applicant: Aurora Operations, Inc.

Inventor： Jake Charland ,  Ethan Eade ,  Karthik Lakshmanan ,  Daniel Munoz ,  Samuel Sean ,  Yuchen Xie ,  Luona Yang

IPC: B60W60/00 ,  G01S7/41 ,  G01S7/48 ,  G01S13/58 ,  G01S17/66 ,  G06T15/08

CPC classification number: B60W60/001 ,  G06T15/08 ,  B60W2420/403 ,  B60W2420/408 ,  B60W2510/0638

Abstract: A method may include obtaining lidar data comprising a plurality of lidar returns from an environment of an autonomous vehicle. The lidar data may be processed with a machine learning model to generate, for the plurality of lidar returns, a plurality of first outputs that each identify a respective lidar return as belonging to an object or non-object and a plurality of second outputs that identify lidar returns belonging to objects as harmful or non-harmful to the autonomous vehicle. A subset of the lidar returns identified as belonging to objects that (i) do not correspond to any of a plurality of pre-classified objects and (ii) were identified as harmful to the autonomous vehicle may be determined. The autonomous vehicle may be controlled based at least in part on the subset of lidar returns.

公开(公告)号：US20240300525A1

公开(公告)日：2024-09-12

申请号：US18269209

申请日：2021-12-17

Applicant: Aurora Operations, Inc.

Inventor： James Andrew Bagnell ,  Arun Venkatraman ,  Sanjiban Choudhury ,  Venkatraman Narayanan

IPC: B60W60/00 ,  G06N20/00

CPC classification number: B60W60/001 ,  G06N20/00 ,  B60W2554/4026 ,  B60W2554/4029 ,  B60W2556/10

Abstract: Systems and methods related to controlling an autonomous vehicle (“AV”) are described herein. Implementations can process actor(s) from a past episode of locomotion of a vehicle, and stream(s) in an environment of the vehicle during the past episode to generate predicted output(s). The actor(s) may each be associated with a corresponding object in the environment of the vehicle, and the stream(s) may each represent candidate navigation paths in the environment of the vehicle. Further, implementations can process the predicted output(s) to generate further predicted output(s), and can compare the predicted output(s) to associated reference label(s). The processing can be performed utilizing layer(s) or distinct, additional layer(s) of machine learning (“ML”) model(s). Implementations can update the layer(s) or the additional layer(s) based on the comparing, and subsequently use the ML model(s) in controlling the AV.

公开(公告)号：US12085674B2

公开(公告)日：2024-09-10

申请号：US17824820

申请日：2022-05-25

Applicant: Aurora Operations, Inc.

Inventor： Lei Wang ,  Sen Lin ,  Andrew Steil Michaels

IPC: G01C3/08 ,  G01S7/481 ,  H01S5/02253

CPC classification number: G01S7/4814 ,  H01S5/02253

Abstract: A light detection and ranging (LIDAR) device includes a first wafer layer, a laser assembly disposed on the first wafer layer, a capping layer, a second wafer layer, and a photonic integrated circuit (PIC). The capping layer is coupled to the first wafer layer and configured to seal the laser assembly. The second wafer layer is at least partially coupled to the first wafer layer. The PIC is formed on the second wafer layer. The second wafer includes an exit feature configured to outcouple laser light from the laser assembly.

公开(公告)号：US12071144B2

公开(公告)日：2024-08-27

申请号：US17139481

申请日：2020-12-31

Applicant: Aurora Operations, Inc.

Inventor： Tian Lan ,  Galen Clark Haynes ,  Alexander David Styler

IPC: B60W50/00 ,  B60W30/00 ,  B60W30/095 ,  G05D1/00 ,  G06T7/20 ,  G06V20/58 ,  G08G1/16

CPC classification number: B60W50/0097 ,  B60W30/00 ,  B60W30/0953 ,  B60W30/0956 ,  G05D1/0088 ,  G05D1/0214 ,  G06T7/20 ,  G06V20/58 ,  G06V20/584 ,  G08G1/166 ,  B60W2554/00 ,  G06T2207/30241 ,  G06T2207/30261

Abstract: Systems and methods for determining object motion and controlling autonomous vehicles are provided. In one example embodiment, a computing system includes processor(s) and one or more tangible, non-transitory, computer readable media that collectively store instructions that when executed by the processor(s) cause the computing system to perform operations. The operations include obtaining data associated with a first object and one or more second objects within a surrounding environment of an autonomous vehicle. The operations include determining an interaction between the first object and the one or more second objects based at least in part on the data. The operations include determining one or more predicted trajectories of the first object within the surrounding environment based at least in part on the interaction between the first object and the one or more second objects. The operations include outputting data indicative of the one or more predicted trajectories of the first object.

公开(公告)号：US12044535B2

公开(公告)日：2024-07-23

申请号：US18309256

申请日：2023-04-28

Applicant: Aurora Operations, Inc.

Inventor： Rachel Ahn ,  David Prasser ,  Peter Hansen ,  Robert Zlot

IPC: G01C21/32 ,  G01C21/30 ,  G01S19/45

CPC classification number: G01C21/32 ,  G01C21/30 ,  G01S19/45

Abstract: Various examples are directed to systems and methods for locating a vehicle. A pose state estimator may access a previous position for the vehicle at a first time, wherein the previous position is on a first sub-map of a plurality of sub-maps. The pose state estimator may receive from a first localizer a first position estimate for the vehicle at a second time after the first time. The first position estimate may be on a second sub-map of the plurality of sub-maps. The pose state estimator may send to a second localizer a sub-map change message indicating the second sub-map.

公开(公告)号：US20240219574A1

公开(公告)日：2024-07-04

申请号：US18404620

申请日：2024-01-04

Applicant: Aurora Operations, Inc.

Inventor： Sen Lin ,  Andrew Steil Michaels

IPC: G01S17/931 ,  G01S7/484 ,  G01S7/4863

CPC classification number: G01S17/931 ,  G01S7/484 ,  G01S7/4863

Abstract: A light detection and ranging (LIDAR) sensor system includes a plurality of LIDAR pixels and a local oscillator module. The local oscillator module is coupled to the plurality of LIDAR pixels. The local oscillator module includes a first local oscillator input configured to receive a first local oscillator signal and a second local oscillator input configured to receive a second local oscillator signal. The local oscillator module is configured to provide the first local oscillator signal or the second local oscillator signal to a first LIDAR pixel of the plurality of LIDAR pixels.

公开(公告)号：US20240219566A1

公开(公告)日：2024-07-04

申请号：US18149008

申请日：2022-12-30

Applicant: Aurora Operations, Inc.

Inventor： Ashish Bhardwaj ,  Amir Hosseini

IPC: G01S17/58 ,  H01S5/024 ,  H01S5/343

CPC classification number: G01S17/58 ,  H01S5/02461 ,  H01S5/343 ,  H01S5/0656

Abstract: A LIDAR system comprising a laser configured to output a beam, a modulator configured to receive the beam and modulate the beam to generate a modulated beam, a photonic integrated circuit having an amplifier coupled to receive the modulated beam from the modulator and generate an amplified beam, the amplifier having an active layer and an alternating or periodic or a super lattice structure configured to dissipate heat; and a transceiver chip coupled to the photonic integrated circuit, the transceiver chip configured to emit the amplified beam and receive a reflected beam from a target.

公开(公告)号：US20240217558A1

公开(公告)日：2024-07-04

申请号：US18471690

申请日：2023-09-21

Applicant: Aurora Operations, Inc.

Inventor： Sanjiban Choudhury ,  Sumit Kumar ,  Micol Marchetti-Bowick

IPC: B60W60/00

CPC classification number: B60W60/00272 ,  B60W2554/4045 ,  B60W2556/00 ,  G06Q50/30

Abstract: Example aspects of the present disclosure relate to an example computer-implemented method for predicting the intent of actors within an environment. The example method includes obtaining state data associated with a plurality of actors within the environment and map data indicating a plurality of lanes of the environment. The method includes determining a plurality of potential goals each actor based on the state data and the map data. The method includes processing the state data, the map data, and the plurality of potential goals with a machine-learned forecasting model to determine (i) a forecasted goal for a respective actor of the plurality of actors, (ii) a forecasted interaction between the respective actor and a different actor of the plurality of actors based on the forecasted goal, and (iii) a continuous trajectory for the respective actor based on the forecasted goal.

公开(公告)号：US12013704B2

公开(公告)日：2024-06-18

申请号：US16839208

申请日：2020-04-03

Applicant: Aurora Operations, Inc.

Inventor： Bryan John Nagy ,  Robert Michael S Dean ,  Jian Wen

IPC: G05D1/00 ,  G01C21/34

CPC classification number: G05D1/0221 ,  G01C21/3407 ,  G05D1/0088 ,  G05D1/0217

Abstract: Examples described herein are directed to systems and methods for autonomous vehicle control system testing. A testing utility may receive log data describing a first location of a capturing vehicle at a first driven route time and a second location of the capturing vehicle at a second drive route time. The testing utility may, using at least the location data, determine a first routing graph modification to constrain a navigator component of an autonomous vehicle control system under test. The testing utility may provide the first routing graph modification to the navigator component to cause the navigator component to generate a testing route.

公开(公告)号：US20240192378A1

公开(公告)日：2024-06-13

申请号：US18415049

申请日：2024-01-17

Applicant: Aurora Operations, Inc.

Inventor： Warren Smith ,  Ethan Eade ,  Sterling J. Anderson ,  James Andrew Bagnell ,  Bartholomeus C. Nabbe ,  Christopher Paul Urmson

IPC: G01S17/931 ,  G06T7/70 ,  G06V20/58

CPC classification number: G01S17/931 ,  G06T7/70 ,  G06V20/58 ,  G06T2207/10028 ,  G06T2207/30261

Abstract: Determining classification(s) for object(s) in an environment of autonomous vehicle, and controlling the vehicle based on the determined classification(s). For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be controlled based on determined pose(s) and/or classification(s) for objects in the environment. The control can be based on the pose(s) and/or classification(s) directly, and/or based on movement parameter(s), for the object(s), determined based on the pose(s) and/or classification(s). In many implementations, pose(s) and/or classification(s) of environmental object(s) are determined based on data from a phase coherent Light Detection and Ranging (LIDAR) component of the vehicle, such as a phase coherent LIDAR monopulse component and/or a frequency-modulated continuous wave (FMCW) LIDAR component.